© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 109366
    Prev
    Next
    INDEX
    Explanations

    inbound size direction swings

    np_acts-logits-general · gemini-2.5-flash-lite

    limericks or mysteries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ૨
    0.57
    وی
    0.53
     अक्सर
    0.51
    わかり
    0.51
    ۲
    0.49
    一般的な
    0.49
     ஏற்கனவே
    0.48
    மாறு
    0.48
    ২
    0.47
     பெரும்பாலான
    0.47
    POSITIVE LOGITS
     skates
    0.50
     fainting
    0.48
     strolling
    0.45
     pins
    0.45
     rings
    0.44
    <0xB1>
    0.44
     Clara
    0.44
    ืม
    0.43
     dữ
    0.42
     zooming
    0.42
    Activations Density 0.001%

    No Known Activations